The Fine tuning of Language models for automation of Humor Detection

Main Article Content

Tavishee Chauhan
Hemant Palivela


In this paper, we propose a method that showcases a novel approach for humor identification using ALBERT and automation of best fit loss function identification and also the Optimiser identification. We have used two configurations of ALBERT, Albert-base and Albert-large. Using different hyper-parameters, we compare their results to obtain the best results for the binary classification problem of detecting texts that are humorous and those that are not humorous. We also determine the best optimizer and loss function that can be used to achieve state-of-the-art performance. The proposed system has been evaluated using metrics that include accuracy, precision, recall, F1-score, and the amount of time required. Among multiple loss functions, Adafactor on Albert-base model have shown promising results with 99\% of accuracy. Paper also talks about comparison of the proposed approach with other language models like BERT, ROBERTa to see a steep decline of 1/3rd in the time taken to train the model on 160K sentences.

Article Details

How to Cite
Chauhan, T., & Palivela, H. (2021). The Fine tuning of Language models for automation of Humor Detection. INFOCOMP Journal of Computer Science, 20(2). Retrieved from
Machine Learning and Computational Intelligence
Author Biography

Hemant Palivela

Hemant Palivela is Head of AI and Machine Learning at eClerx Services LTD. He has been awarded the prestigious 40 under 40 Data Scientists by Analytical India Magazine 2021. After spending nearly seven years working with renowned organizations like NMIMS and Aureus Analytics, he shifted to Centre of Excellence, Digital Analytics Division of eClerx where he works on Campaign Analytics, Speech Processing, Natural Language Understanding/Generation and Recommendation Systems. His principal areas of interest with reference to the theoretical frame include, Machine learning optimization, linear algebra, probability theory, and practical frame include, drug discovery, insurance analytics, and recommendation systems. He has published around 35 plus research papers in International Conference and Journals. He has done his Bachelor's, Master's and Doctorate in Computer Engineering